© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 23422
    Prev
    Next
    INDEX
    Explanations

    general terms or phrases indicating inclusivity or a broad scope

    oai_token-act-pair · gpt-3.5-turbo

    the word "all" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hran
    -0.71
    culosis
    -0.68
    ydia
    -0.67
    atts
    -0.65
    IND
    -0.62
     Gw
    -0.61
     Kamp
    -0.61
    isu
    -0.61
    agus
    -0.59
    yip
    -0.58
    POSITIVE LOGITS
     attendant
    1.01
     associated
    0.89
     alike
    0.86
     accompanying
    0.85
     thereof
    0.82
     ensuing
    0.82
     assorted
    0.78
     subsequent
    0.78
    abouts
    0.74
    usions
    0.73
    Activations Density 0.093%

    No Known Activations